Celigo has launched MCP Management to govern how AI assistants and agents access business systems. The product is aimed at IT and security teams that need oversight of AI activity across enterprise software.
The offering provides a single control layer for both Celigo-built and third-party Model Context Protocol servers, which are increasingly used to let AI tools connect with software across the business. It enables teams to authenticate users, define access at the level of individual tools and maintain an auditable record of AI activity.
Model Context Protocol, or MCP, has emerged as a standard for linking AI assistants and agents to business systems. Software suppliers have begun offering their own MCP servers, with each server exposing specific actions an AI tool can carry out, such as checking a customer record in a CRM system, reviewing an invoice in an ERP platform or updating a service ticket.
That expansion has widened access beyond specialist integration teams to employees using assistants such as Claude, ChatGPT, Copilot and Cursor, as well as autonomous agents that can act without direct human input. Celigo argues this shift has created governance problems because many MCP servers rely on broad default access and shared service credentials, making it harder to identify who was behind a specific action.
Matt Graney, Chief Product Officer at Celigo, said the company was addressing a gap in enterprise controls around AI-based actions.
"AI assistants and agents are a new class of actors in the enterprise, and the old model of shared credentials and broad access was never designed for them. Enterprises need to know who is behind every AI request, what it is authorised to do and what actions it has taken," Graney said.
"MCP Management gives IT one governed path. Every call traces back to a real person, access is approved one tool at a time, and because Celigo runs the tools as well as governs them, teams can see exactly which systems AI touched and what it changed," he added.
Control layer
Within Celigo's framework, every MCP server runs behind what it calls an MCP Gateway. Through that gateway, administrators can determine which tools each employee can use, with access linked to the organisation's identity provider rather than shared application credentials.
Celigo has also introduced an MCP Registry, designed to show every MCP server in use across an organisation, the AI assistants or agents using them and the people with access. Staff can request use of specific tools, while administrators approve access on a tool-by-tool basis.
According to the company, the platform differs from standalone gateways because it both governs tools and executes them. That means companies can see which systems were accessed, what changed during a workflow and where a process failed.
Another element of the launch is the ability to build composite tools that draw on multiple systems in a single action. For example, a finance-focused agent could retrieve an order from a CRM platform, invoice details from an ERP system and payment status from a billing tool in one call, without receiving full application access to each system.
Customer views
Nidecker Group, which uses Celigo, said the approach gives it a fuller operational view across third-party tools.
"Celigo's MCP was the missing piece. It's the layer in the middle connecting to all our third-party tools in the cloud. Now we get the start, the middle and the end in one dashboard. That's a total game changer for analytics and visibility," said Millet.
Celigo is positioning the product within its wider automation platform, which already covers data integration, API management, EDI and application workflows. The setup allows customers to manage AI-related access controls in the same environment as other business integrations, including links to on-premises and legacy systems that may not have their own MCP servers.
Interplay Learning, another customer, said that matters because many of its existing operational processes already run through the platform.
"Through an acquisition, system consolidation and workflows tailored to how we operate, Celigo has been a consistent platform for connecting data and systems across our business. From sales and commerce to billing and fulfillment, our core operations run on it. That foundation puts us in a stronger position as we expand our use of automation and AI, because our systems and data are already working together," said Lanham.